datakit
Version:
Simple JavaScript toolkit for data transform across JSON, CSV and YAML.
207 lines • 11.3 kB
JavaScript
;
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
var __generator = (this && this.__generator) || function (thisArg, body) {
var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
function verb(n) { return function (v) { return step([n, v]); }; }
function step(op) {
if (f) throw new TypeError("Generator is already executing.");
while (g && (g = 0, op[0] && (_ = 0)), _) try {
if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
if (y = 0, t) op = [op[0] & 2, t.value];
switch (op[0]) {
case 0: case 1: t = op; break;
case 4: _.label++; return { value: op[1], done: false };
case 5: _.label++; y = op[1]; op = [0]; continue;
case 7: op = _.ops.pop(); _.trys.pop(); continue;
default:
if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
if (t[2]) _.ops.pop();
_.trys.pop(); continue;
}
op = body.call(thisArg, _);
} catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
}
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.documentation = exports.main = void 0;
var user_fn_1 = require("./lib/user-fn");
var io_1 = require("../lib/io");
var verify_1 = require("../lib/verify");
var help_1 = require("./lib/help");
function main(argv) {
return __awaiter(this, void 0, void 0, function () {
var exampleFn, leftSelectorFn, left, rightSelectorFn, right, mergeFn, leftKeys, rightKeys, leftMap, i, record, key, rightMap, i, record, key, combinations, output, _loop_1, leftIndex, _loop_2, rightIndex;
return __generator(this, function (_a) {
switch (_a.label) {
case 0:
exampleFn = "r => r.key";
leftSelectorFn = (0, user_fn_1.loadUserFn)(argv, exampleFn);
return [4 /*yield*/, (0, io_1.inputData)(argv)];
case 1:
left = _a.sent();
(0, verify_1.verifyArray)(left, "left dataset", "intersect");
rightSelectorFn = (0, user_fn_1.loadUserFn)(argv, exampleFn);
return [4 /*yield*/, (0, io_1.inputData)(argv)];
case 2:
right = _a.sent();
(0, verify_1.verifyArray)(right, "right dataset", "intersect");
mergeFn = (0, user_fn_1.loadUserFn)(argv, "(left, right) => merge(left, right)");
leftKeys = left.map(function (record) {
return (0, user_fn_1.invokeUserFn)(function () { return leftSelectorFn.fn(record); }, leftSelectorFn.details);
});
rightKeys = right.map(function (record) {
return (0, user_fn_1.invokeUserFn)(function () { return rightSelectorFn.fn(record); }, rightSelectorFn.details);
});
leftMap = {};
for (i = 0; i < left.length; ++i) {
record = left[i];
key = leftKeys[i];
if (leftMap[key] === undefined) {
leftMap[key] = [];
}
leftMap[key].push({
record: record,
index: i,
});
}
rightMap = {};
for (i = 0; i < right.length; ++i) {
record = right[i];
key = rightKeys[i];
if (rightMap[key] === undefined) {
rightMap[key] = [];
}
rightMap[key].push({
record: record,
index: i,
});
}
combinations = {};
output = [];
_loop_1 = function (leftIndex) {
var leftRecord = left[leftIndex];
var leftKey = leftKeys[leftIndex];
var rightMatches = rightMap[leftKey];
if (rightMatches && rightMatches.length > 0) {
var _loop_3 = function (right_1) {
var rightIndex = right_1.index;
var comboKey = "".concat(leftIndex, "-").concat(rightIndex);
if (!combinations[comboKey]) {
// This combination is not recorded yet.
combinations[comboKey] = true;
var merged = (0, user_fn_1.invokeUserFn)(function () { return mergeFn.fn(leftRecord, right_1.record); }, mergeFn.details);
if (merged !== undefined) {
output.push(merged);
}
}
};
for (var _i = 0, rightMatches_1 = rightMatches; _i < rightMatches_1.length; _i++) {
var right_1 = rightMatches_1[_i];
_loop_3(right_1);
}
}
else {
var merged = (0, user_fn_1.invokeUserFn)(function () { return mergeFn.fn(leftRecord, undefined); }, mergeFn.details);
if (merged !== undefined) {
output.push(merged);
}
}
};
for (leftIndex = 0; leftIndex < left.length; ++leftIndex) {
_loop_1(leftIndex);
}
_loop_2 = function (rightIndex) {
var rightRecord = right[rightIndex];
var rightKey = rightKeys[rightIndex];
var leftMatches = leftMap[rightKey];
if (leftMatches && leftMatches.length > 0) {
var _loop_4 = function (left_1) {
var leftIndex = left_1.index;
var comboKey = "".concat(leftIndex, "-").concat(rightIndex);
if (!combinations[comboKey]) {
// This combination is not recorded yet.
combinations[comboKey] = true;
var merged = (0, user_fn_1.invokeUserFn)(function () { return mergeFn.fn(left_1.record, rightRecord); }, mergeFn.details);
if (merged !== undefined) {
output.push(merged);
}
}
};
for (var _b = 0, leftMatches_1 = leftMatches; _b < leftMatches_1.length; _b++) {
var left_1 = leftMatches_1[_b];
_loop_4(left_1);
}
}
else {
var merged = (0, user_fn_1.invokeUserFn)(function () { return mergeFn.fn(undefined, rightRecord); }, mergeFn.details);
if (merged !== undefined) {
output.push(merged);
}
}
};
for (rightIndex = 0; rightIndex < right.length; ++rightIndex) {
_loop_2(rightIndex);
}
return [4 /*yield*/, (0, io_1.outputData)(argv, output)];
case 3:
_a.sent();
return [2 /*return*/];
}
});
});
}
exports.main = main;
exports.documentation = {
name: "intersect",
desc: "Aggregates two data sets with common keys kind of like an SQL join.",
syntax: "intersect <left-key-selector-fn> <left-input-file> <right-key-selector-fn> <right-input-file> <merge-fn> [<output-file>]",
inputs: help_1.standardCmdInputs,
inputCount: 2,
outputs: help_1.standardCmdOutputs,
args: [
{
name: "left-key-selector-fn",
desc: "A JavaScript function to select the join key for each record of the left dataset. Specifying a file name will load the JavaScript code from the file.",
},
{
name: "left-input-file",
desc: help_1.standardInputFileHelpDesc,
},
{
name: "right-key-selector-fn",
desc: "A JavaScript function to select the join key for each record of the right dataset. Specifying a file name will load the JavaScript code from the file.",
},
{
name: "right-input-file",
desc: help_1.standardInputFileHelpDesc,
},
{
name: "merge-fn",
desc: "A JavaScript function to merge records from left and right datasets. Specifying a file name will load the JavaScript code from the file.",
},
help_1.standardOutputFileHelp,
],
examples: [
{
name: "Reads two JSON files and merges the datasets based on the \"email\" field, writes output to a JSON file",
cmd: 'intersect "r => r.email" left-input.json "r => r.email" right-input.json "(left, right) => ({ ...left, ...right })" output.json',
},
],
notes: [
"You can only read input data from standard input from one of the left or right datasets.",
]
};
//# sourceMappingURL=intersect.js.map